andreapiso

Seems slow. What resolution are you using as input? On Sat, 27 May 2017 at 2:15 PM, kaishijeng wrote: > It works now. On speed performance, I found SqueezeDet is...

Tensorflow always allocates all your GPU memory by default. There is a tensorflow setting to prevent this from happening if you do not want that.

What do you get out of doing detection+classification in a single net? The detection net will already classify the objects in the picture... On Fri, 22 Sep 2017 at 10:16...

Anchor boxes are dataset dependent. You should run k-means on your dataset boxes beforehand to know which ones to use. On Fri, 9 Jun 2017 at 8:46 AM, ByoenghakYim wrote:...

Can't you just use k-means on the boxes of your dataset?

Anchor boxes are just shapes, what would be the meaning of calculating their center? On Fri, 9 Feb 2018 at 9:33 PM, Tejas wrote: > Do we have to run...

+1

This change would be great as it kind of "merges" the API V1 and V2 providing great flexibility. Can these classes be defined programmatically like in the API V1? In...

> Hi @andreapiso , for this use case, how would you imagine sending requests to these two models? If two models are trained separately, you can directly use different route_prefix...

If you want to support multiple apps, you will need to use `deploy` until the changes discussed in the RFC make it in.